English
Related papers

Related papers: Towards Atoms of Large Language Models

200 papers

Model ensembles are effective tools for estimating prediction uncertainty in deep learning atomistic force fields. However, their widespread adoption is hindered by high computational costs and overconfident error estimates. In this work,…

Machine Learning · Computer Science 2024-05-24 Joshua A. Vita , Amit Samanta , Fei Zhou , Vincenzo Lordi

Large language models (LLMs) exhibit remarkable problem-solving abilities, but struggle with complex tasks due to static internal knowledge. Retrieval-Augmented Generation (RAG) enhances access to external information, yet remains limited…

We address the main problem of self-learning LLM: the question of what to learn. We propose a self-learning LLM framework that enables an LLM to independently learn previously unknown knowledge through self-assessment of their own…

Artificial Intelligence · Computer Science 2024-11-13 Teddy Ferdinan , Jan Kocoń , Przemysław Kazienko

Large Language Models (LLMs) stand at the forefront of a number of Natural Language Processing (NLP) tasks. Despite the widespread adoption of LLMs in NLP, much of their potential in broader fields remains largely unexplored, and…

Machine Learning · Computer Science 2024-03-11 Zhiqiang Zhong , Kuangyu Zhou , Davide Mottin

Large language models (LLMs) such as generative pretrained transformers (GPTs) have shown potential for various commercial applications, but their applicability for materials design remains underexplored. In this article, we introduce…

Materials Science · Physics 2024-07-02 Kamal Choudhary

Atomism is the view that everything is composed of atoms. The view within the framework of the contemporary formal approach is expressed on the ground of mereology with the use of the primitive notion of being a part as every object has at…

Logic · Mathematics 2023-10-24 Marcin Łyczak

Understanding how explicit theoretical features are encoded in opaque neural systems is a central challenge now common to neuroscience and AI. We introduce Metric Learning Encoding Models (MLEMs) to address this challenge most directly as a…

Computation and Language · Computer Science 2025-11-17 Louis Jalouzot , Christophe Pallier , Emmanuel Chemla , Yair Lakretz

As large language models (LLMs) become integrated into everyday and high-stakes decision-making, they inherit the ambiguity and biases of human language. While they produce fluent and coherent outputs, they rely on statistical pattern…

Artificial Intelligence · Computer Science 2026-04-17 Rikard Rosenbacke , Carl Rosenbacke , Victor Rosenbacke , Martin McKee

Large Language Models (LLMs) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs inner mechanisms through the lens of geometry. In…

Artificial Intelligence · Computer Science 2024-07-12 Randall Balestriero , Romain Cosentino , Sarath Shekkizhar

A new method is presented to generate atomic structures that reproduce the essential characteristics of arbitrary material systems, phases, or ensembles. Previous methods allow one to reproduce the essential characteristics (e.g. chemical…

Materials Science · Physics 2024-09-24 James M. Goff , Coreen Mullen , Shizhong Yang , Oleg N. Starovoytov , Mitchell A. Wood

The ability to translate diverse patterns of inputs into structured patterns of behavior has been thought to rest on both humans' and machines' ability to learn robust representations of relevant concepts. The rapid advancement of…

Artificial Intelligence · Computer Science 2025-10-02 Zach Studdiford , Timothy T. Rogers , Kushin Mukherjee , Siddharth Suresh

Large Language Models (LLMs) have demonstrated impressive capabilities, yet their deployment in high-stakes domains is hindered by inherent limitations in trustworthiness, including hallucinations, instability, and a lack of transparency.…

Computation and Language · Computer Science 2025-10-21 David Peer , Sebastian Stabinger

Large language models (LLMs) exhibit systematic miscalibration with rhetorical intensity not proportionate to epistemic grounding. This study tests this hypothesis and proposes a framework for quantifying this decoupling by designing a…

Computation and Language · Computer Science 2026-04-23 Asim D. Bakhshi

Evaluating large language models (LLMs) typically requires thousands of benchmark items, making the process expensive, slow, and increasingly impractical at scale. Existing evaluation protocols rely on average accuracy over fixed item sets,…

Computation and Language · Computer Science 2026-02-03 Peiyu Li , Xiuxiu Tang , Si Chen , Ying Cheng , Ronald Metoyer , Ting Hua , Nitesh V. Chawla

Over the past decade, Artificial Intelligence (AI) has had great success recently and is being used in a wide range of academic and industrial fields. More recently, LLMs have made rapid advancements that have propelled AI to a new level,…

Machine Learning · Computer Science 2024-06-17 Da Song , Xuan Xie , Jiayang Song , Derui Zhu , Yuheng Huang , Felix Juefei-Xu , Lei Ma

Motivated by the remarkable success of artificial intelligence (AI) across diverse fields, the application of AI to solve scientific problems, often formulated as partial differential equations (PDEs), has garnered increasing attention.…

Machine Learning · Computer Science 2025-10-21 Rohan Bhatnagar , Ling Liang , Krish Patel , Haizhao Yang

Large language models (LLMs) are evaluated for calibration using metrics such as Expected Calibration Error that conflate two distinct components: the model's ability to discriminate correct from incorrect answers (sensitivity) and its…

Computation and Language · Computer Science 2026-03-17 Jon-Paul Cacioli

Data-driven schemes that associate molecular and crystal structures with their microscopic properties share the need for a concise, effective description of the arrangement of their atomic constituents. Many types of models rely on…

Machine Learning · Statistics 2022-06-08 Jigyasa Nigam , Sergey Pozdnyakov , Guillaume Fraux , Michele Ceriotti

Existing explainability methods for Large Language Models (LLMs) typically treat hidden states as static points in activation space, assuming that correct and incorrect inferences can be separated using representations from an individual…

Computation and Language · Computer Science 2026-03-03 Hamed Damirchi , Ignacio Meza De la Jara , Ehsan Abbasnejad , Afshar Shamsi , Zhen Zhang , Javen Shi

Models of Asymmetric Dark Matter (ADM) with a sufficiently attractive and long-range force gives rise to stable bound objects, analogous to nuclei in the Standard Model, called nuggets. We study the properties of these nuggets and compute…

High Energy Physics - Phenomenology · Physics 2017-11-22 Moira I. Gresham , Hou Keong Lou , Kathryn M. Zurek
‹ Prev 1 3 4 5 6 7 10 Next ›